README.md

---
license: other
license_name: bespoke-lora-trained-license
license_link: https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=Image&allowDerivatives=True&allowDifferentLicense=True
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
- migrated
- photorealistic
- sexy
- woman
- actor
- celebrity
- cute
- girls
- realistic
- pretty
- influencer
- jennifer carpenter

base_model: black-forest-labs/FLUX.1-dev
instance_prompt: c4rp3
widget:
- text: 'woman, light makeup, sweater, smiling, kitchen'
  
  output:
    url: >-
      28002660.jpeg
- text: 'woman, light makeup, sitting at a table wearing a light grey sweatshirt, holding a sign that has the handwriting "Welcome to FLUX!!" written on it. She is looking at the camera and in the background are some office plants on either side of her out of focus'
  
  output:
    url: >-
      28002661.jpeg
- text: 'woman, light makeup, Expressionistic abstract painting utilizing a rough palette knife technique depicting the face of a woman with long flowing hair in the fall. The autumn theme is respresented through primary use of the colors red, orange and brown as well as autumn trees and leaves'
  
  output:
    url: >-
      28002658.jpeg
- text: 'woman, light makeup,kodachrome, neon,cyberpunk, looking at viewer, frontview'
  
  output:
    url: >-
      28002662.jpeg
- text: 'woman, light makeup, wearing a basketball jersey, at a basketball court, looking at camera'
  
  output:
    url: >-
      28002663.jpeg

---

# Jennifer Carpenter 2012 Flux and SDXL 

<Gallery />





## Model description

<h2 id="flux-n6m8np7yu"><strong><span style="color:rgb(253, 126, 20)">Flux</span></strong></h2><p>Jennifer Carpenter in 2012.. All sample images are with no face detailer or hi-res fix, they are 1024x1024 resolution. They are generated on Euler at 20 steps. This lora is trained on 1024x1024 resolution as well. I used flux dev in the sample images.I recommend putting "light makeup" some where in your prompt. I've done testing and there are 2 ways my loras usually work best:</p><p></p><ol><li><p>Strength at 0.9-1 with no trigger word</p></li><li><p>Strength at 0.85-.0.95 with trigger word: c4rp3</p></li></ol><p></p><p><span style="color:rgb(193, 194, 197)">i use comfy ui and theres a strength_clip option in the lora node and i set it to 0.85. Idk whats best but thats what i do</span></p><h2 id="sdxl-s1vw5tjek"><strong><span style="color:rgb(253, 126, 20)">SDXL</span></strong></h2><p>Jennifer Carpenter in 2012. I recommend putting "light makeup" at the end of the prompt and seeing if it brings better results, if not just remove it. It depends on the checkpoint. This goes all my loras of women.</p><p></p><p><span style="color:rgb(193, 194, 197)">put this in negative prompt: </span><strong><span style="color:rgb(193, 194, 197)">ugly, deformed, airbrushed, photoshop, rendered, (multiple people), blurry, child, mouth open<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/1886b959-733f-4060-ba02-f8810ad87a47/width=525/1886b959-733f-4060-ba02-f8810ad87a47.jpeg" /></span></strong></p>

## Trigger words
You should use `c4rp3`, `light makeup` to trigger the image generation.
    

## Download model

Weights for this model are available in Safetensors format.

[Download](/Keltezaa/jennifer-carpenter-2012-flux-and-sdxl/tree/main) them in the Files & versions tab.

## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)

```py
from diffusers import AutoPipelineForText2Image
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to(device)
pipeline.load_lora_weights('Keltezaa/jennifer-carpenter-2012-flux-and-sdxl', weight_name='Jennifer_Carpenter_2012_Flux.safetensors')
image = pipeline('woman, light makeup, wearing a basketball jersey, at a basketball court, looking at camera').images[0]
```

For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)